keras-team/keras · error · ValueError

Invalid value for argument `depth_multiplier`. Expected a st

Error message

Invalid value for argument `depth_multiplier`. Expected a strictly positive value. Received depth_multiplier={self.depth_multiplier}.

What it means

Depthwise convolution layers require depth_multiplier to be strictly positive; zero or negative values would produce zero output channels. __init__ of DepthwiseConv1D/2D/3D validates this immediately.

Source

Thrown at keras/src/layers/convolutional/base_depthwise_conv.py:132

        self.strides = standardize_tuple(strides, rank, "strides")
        self.dilation_rate = standardize_tuple(
            dilation_rate, rank, "dilation_rate"
        )
        self.padding = standardize_padding(padding)
        self.data_format = standardize_data_format(data_format)
        self.activation = activations.get(activation)
        self.use_bias = use_bias
        self.depthwise_initializer = initializers.get(depthwise_initializer)
        self.bias_initializer = initializers.get(bias_initializer)
        self.depthwise_regularizer = regularizers.get(depthwise_regularizer)
        self.bias_regularizer = regularizers.get(bias_regularizer)
        self.depthwise_constraint = constraints.get(depthwise_constraint)
        self.bias_constraint = constraints.get(bias_constraint)
        self.input_spec = InputSpec(min_ndim=self.rank + 2)
        self.data_format = self.data_format

        if self.depth_multiplier is not None and self.depth_multiplier <= 0:
            raise ValueError(
                "Invalid value for argument `depth_multiplier`. Expected a "
                "strictly positive value. Received "
                f"depth_multiplier={self.depth_multiplier}."
            )

        if not all(self.kernel_size):
            raise ValueError(
                "The argument `kernel_size` cannot contain 0. Received "
                f"kernel_size={self.kernel_size}."
            )

        if not all(self.strides):
            raise ValueError(
                "The argument `strides` cannot contains 0. Received "
                f"strides={self.strides}"
            )

    def build(self, input_shape):

View on GitHub (pinned to 7a34a03db6)

Solutions

1. Set depth_multiplier to a positive integer (typically 1).
2. Clamp computed values: max(1, int(value)).
3. Check the config/sweep bounds producing the value.

Example fix

# before
layer = keras.layers.DepthwiseConv2D(3, depth_multiplier=0)

# after
layer = keras.layers.DepthwiseConv2D(3, depth_multiplier=1)

assert depth_multiplier is None or (isinstance(depth_multiplier, int) and depth_multiplier > 0)

def valid_depth_multiplier(dm) -> bool:
    return dm is None or (isinstance(dm, int) and dm > 0)

When it happens

Trigger: Passing depth_multiplier=0 or a negative value (often computed from config or a sweep) when constructing keras.layers.DepthwiseConv2D or 1D/3D variants.

Common situations: Hyperparameter search yielding 0; depth_multiplier computed from a channel count or ratio that underflows to 0; copy-paste from a SeparableConv config.

Related errors

• The argument `kernel_size` cannot contain 0. Received kernel
• The argument `strides` cannot contains 0. Received strides={
• Invalid value for argument `depth_multiplier`. Expected a st
• If using `weights="imagenet"` as true, `classes` should be 1
• The number of repeats in `EfficientNet` must be > 0. Receive

AI-assisted analysis of keras-team/keras@7a34a03db6 (2026-08-25). Data as JSON: /api/errors/bfb62b41fcecefe1. Report an issue: GitHub.